deposit_your_work

Using reinforcement learning to control advanced life support systems

Files in this item

Files Size Format View
1425842.PDF 12.13Mb application/pdf Thumbnail

Show full item record

Item Metadata

Title: Using reinforcement learning to control advanced life support systems
Author: Klein, Theresa J.
Advisor: Subramanian, Devika
Degree: Master of Science thesis
Abstract: This thesis deals with the application of reinforcement learning techniques to the control of a closed life support system simulator, such as could be used on a long duration space mission. We apply reinforcement learning to two different aspects of the simulator, control of recycling subsystems, and control of crop planting schedules. Comparisons are made between distributed and centralized controllers, generalized and non-generalized RL, and between different approaches to the construction of the state table and the design of reward functions. Distributed controllers prove to be superior to centralized controllers both in terms of speed and performance of the controller. Generalization helps to speed convergence, but the performance of the policy derived is dependent on the shape of the reward function.
Citation: Klein, Theresa J.. (2005) "Using reinforcement learning to control advanced life support systems." Masters Thesis, Rice University. http://hdl.handle.net/1911/17794.
URI: http://hdl.handle.net/1911/17794
Date: 2005

This item appears in the following Collection(s)